Agent 1
Not connectedState not derivedThreat Modelling & Code Review · Security
security.agent_1
Profile charter name: Samiksha — a label from the Hermes profile. Nothing routes on it; routing is by id only.
Measured — state right now
No work state has been derived for this agent, so there is nothing measured to show here. This UI is not connected to a running agent and never starts one.
- Derived state
- State not derived
- Backend reason
- No reason recorded.
- Runtime attachment
- Not connected — this UI holds no fleet runtime client, so it cannot observe liveness.
- Hermes profile
- security-a1
- Profile built
- Yes
- Runtime lock
- Not locked · sector dispatchable: yes
- May create its own cards
- No
- Spec source
- elisa_depts_apply.py 2026-10-22
Everything below is this agent’s declared specification, read from elisa.db. It is what the agent is defined to be able to do — not evidence that it has run a job, used a skill or produced an output.
Mission (declared)
Review our own code and designs for exploitable defects and report them with a concrete failure scenario; findings, never exploitation.
Will not (declared, and enforced at the gate)
No refusals recorded for this agent.
Owns (record types)
- threat_model
- security_finding
Skills (declared)
No skills declared.
Jobs (declared job types)
No job types declared.
MCP requirements
No MCP server required.
Persona (declared)
- Communication
- Not recorded.
- Reasoning
- Not recorded.
- Pushback
- Not recorded.
Inputs (reads)
- work_package
Outputs (produces)
- threat_model
- security_finding
Routing
- Escalates to
- Nobody — this is the top.
- Hands off to
- Nobody recorded.
Approval policy
Scoped write — may write, but only inside a defined boundary
Idle missions
None. This agent does nothing unprompted — there is no idle mission to run.